feat: Add workspace: confine agent tools to a folder (#1103)

* feat: Add workspace: confine agent tools to a folder

Pick a server folder as the agent's workspace so its file/shell tools work
there and don't touch files outside it. File tools are hard-confined; bash/
python run with cwd set to the folder.

Includes a slash command: `/workspace` (alias `/ws`) — show / `set <path>` /
`clear` / `pick` (open the directory browser).

- routes/workspace_routes.py: GET /api/workspace/browse (admin-only).
- src/tool_execution.py: hard path confinement for read_file/write_file;
  bash/python cwd. Threaded route → stream_agent_loop → execute_tool_block.
- src/agent_loop.py: workspace note prepended to the system prompt.
- static/: overflow menu item, input-bar pill, directory-browser modal, and
  the /workspace slash command.
- tests/test_workspace_confine.py.

* Wire workspace confinement into tools that landed after this PR

edit_file (#1239) and grep/glob/ls (#1670) merged after workspace-confine was
written, so they bypassed the workspace boundary. Thread the workspace through:
  - edit_file: _do_edit_file resolves via _resolve_tool_path_in_workspace
  - grep/glob/ls: _resolve_search_root confines to the workspace (root + paths)
  - bash/python/bg cwd: workspace or _AGENT_WORKDIR (keep the #2586 data-dir
    default when no workspace is set)
Tests cover edit_file + grep/ls confinement (inside ok, outside rejected).

* Workspace picker: editable path bar + modal style cohesion + cross-platform hardening

- Make the current-folder strip an editable address bar: type/paste a full
  path and press Enter to navigate (also reaches other Windows drives and
  hidden dirs the up-only browser cannot).
- Reuse shared modal CSS: drop bespoke .workspace-modal-content/.workspace-btn*
  in favour of base .modal-content/.modal-body and the .confirm-btn button
  family; separators/hover use var(--border). Net -31 CSS lines.
- Fix the path field overflowing the modal right edge (flex stretch + margin
  vs an overflow:auto scrollbar-feedback loop): full-bleed, no h-margin.
- Cross-platform confinement: normcase the workspace commonpath check so
  containment holds on case-insensitive filesystems (Windows/macOS).
- Make tests OS-portable: sibling temp dirs instead of /etc, python os.getcwd()
  instead of pwd. 5 pass.

routes/chat_routes.py

@@ -2,6 +2,7 @@
 
 import asyncio
 import json
+import os
 import time
 import logging
 from datetime import datetime
@@ -394,6 +395,12 @@ def setup_chat_routes(
         compare_mode = str(form_data.get("compare_mode", "")).lower() == "true"
         incognito = str(form_data.get("incognito", "")).lower() == "true"
         chat_mode = str(form_data.get("mode", "")).lower()  # 'chat' or 'agent'
+        # Workspace: confine the agent's file/shell tools to this folder. Validate
+        # it's a real directory; ignore (no confinement) otherwise.
+        workspace = (form_data.get("workspace") or "").strip()
+        if workspace:
+            _ws_real = os.path.realpath(os.path.expanduser(workspace))
+            workspace = _ws_real if os.path.isdir(_ws_real) else ""
         # Did the USER explicitly pick agent mode? (vs. us auto-escalating
         # below). Skill extraction should only learn from real agent sessions,
         # not chats we quietly promoted for a notes/calendar intent.
@@ -1007,6 +1014,7 @@ def setup_chat_routes(
                         disabled_tools=disabled_tools if disabled_tools else None,
                         owner=_user,
                         fallbacks=_fallback_candidates,
+                        workspace=workspace or None,
                     ):
                         if chunk.startswith("data: ") and not chunk.startswith("data: [DONE]"):
                             try: